diff --git "a/test-en-hu.comet" "b/test-en-hu.comet"
new file mode 100644--- /dev/null
+++ "b/test-en-hu.comet"
@@ -0,0 +1,1013 @@
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 0	score: 0.8357
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 1	score: 0.9001
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 2	score: 0.9152
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 3	score: 0.8252
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 4	score: 0.8792
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 5	score: 0.6228
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 6	score: 0.8345
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 7	score: 0.8749
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 8	score: 0.9025
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 9	score: 0.7407
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 10	score: 0.9170
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 11	score: 0.8639
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 12	score: 0.8823
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 13	score: 0.8864
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 14	score: 0.3322
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 15	score: 0.7771
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 16	score: 0.8274
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 17	score: 0.9378
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 18	score: 0.9184
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 19	score: 0.8873
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 20	score: 0.9683
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 21	score: 0.9443
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 22	score: 0.8315
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 23	score: 0.8927
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 24	score: 0.9003
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 25	score: 0.9402
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 26	score: 0.9265
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 27	score: 0.7303
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 28	score: 0.8296
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 29	score: 0.8973
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 30	score: 0.7199
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 31	score: 0.8342
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 32	score: 0.8934
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 33	score: 0.9137
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 34	score: 0.9430
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 35	score: 0.9455
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 36	score: 0.9146
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 37	score: 0.9105
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 38	score: 0.9118
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 39	score: 0.9105
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 40	score: 0.7542
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 41	score: 0.9203
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 42	score: 0.9205
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 43	score: 0.8910
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 44	score: 0.8241
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 45	score: 0.8570
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 46	score: 0.9240
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 47	score: 0.8683
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 48	score: 0.8584
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 49	score: 0.9139
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 50	score: 0.8722
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 51	score: 0.9235
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 52	score: 0.8234
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 53	score: 0.9326
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 54	score: 0.8494
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 55	score: 0.8933
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 56	score: 0.8061
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 57	score: 0.8582
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 58	score: 0.7940
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 59	score: 0.9592
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 60	score: 0.9501
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 61	score: 0.9464
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 62	score: 0.8495
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 63	score: 0.9223
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 64	score: 0.8554
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 65	score: 0.7778
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 66	score: 0.7357
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 67	score: 0.7969
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 68	score: 0.9436
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 69	score: 0.8883
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 70	score: 0.8717
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 71	score: 0.7581
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 72	score: 0.9001
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 73	score: 0.6962
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 74	score: 0.8866
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 75	score: 0.8858
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 76	score: 0.8553
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 77	score: 0.6275
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 78	score: 0.9487
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 79	score: 0.9195
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 80	score: 0.8952
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 81	score: 0.9503
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 82	score: 0.8768
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 83	score: 0.8615
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 84	score: 0.8362
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 85	score: 0.9270
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 86	score: 0.8272
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 87	score: 0.8710
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 88	score: 0.9282
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 89	score: 0.8503
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 90	score: 0.7537
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 91	score: 0.7694
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 92	score: 0.8645
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 93	score: 0.8013
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 94	score: 0.8975
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 95	score: 0.9539
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 96	score: 0.8992
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 97	score: 0.9119
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 98	score: 0.9513
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 99	score: 0.7667
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 100	score: 0.9331
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 101	score: 0.8468
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 102	score: 0.8765
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 103	score: 0.9309
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 104	score: 0.8234
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 105	score: 0.9116
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 106	score: 0.9108
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 107	score: 0.8646
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 108	score: 0.7423
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 109	score: 0.8376
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 110	score: 0.8771
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 111	score: 0.9147
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 112	score: 0.9338
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 113	score: 0.8513
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 114	score: 0.7757
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 115	score: 0.8980
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 116	score: 0.9088
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 117	score: 0.9292
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 118	score: 0.9599
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 119	score: 0.7957
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 120	score: 0.9163
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 121	score: 0.9328
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 122	score: 0.9537
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 123	score: 0.9712
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 124	score: 0.9034
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 125	score: 0.8831
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 126	score: 0.8828
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 127	score: 0.9090
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 128	score: 0.8440
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 129	score: 0.9295
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 130	score: 0.8808
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 131	score: 0.8690
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 132	score: 0.8934
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 133	score: 0.9575
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 134	score: 0.8022
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 135	score: 0.8695
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 136	score: 0.9171
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 137	score: 0.7999
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 138	score: 0.9354
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 139	score: 0.8552
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 140	score: 0.9129
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 141	score: 0.7851
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 142	score: 0.8440
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 143	score: 0.9082
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 144	score: 0.9220
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 145	score: 0.9244
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 146	score: 0.9235
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 147	score: 0.8907
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 148	score: 0.9092
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 149	score: 0.9297
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 150	score: 0.9075
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 151	score: 0.8944
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 152	score: 0.8626
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 153	score: 0.8241
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 154	score: 0.7328
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 155	score: 0.8137
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 156	score: 0.9027
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 157	score: 0.8997
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 158	score: 0.9316
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 159	score: 0.9084
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 160	score: 0.8847
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 161	score: 0.8099
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 162	score: 0.8177
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 163	score: 0.9117
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 164	score: 0.9360
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 165	score: 0.8409
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 166	score: 0.8607
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 167	score: 0.9208
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 168	score: 0.7730
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 169	score: 0.8943
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 170	score: 0.8012
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 171	score: 0.9237
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 172	score: 0.9100
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 173	score: 0.8695
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 174	score: 0.8842
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 175	score: 0.9558
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 176	score: 0.8286
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 177	score: 0.9277
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 178	score: 0.8601
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 179	score: 0.9211
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 180	score: 0.8458
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 181	score: 0.9084
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 182	score: 0.9410
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 183	score: 0.9642
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 184	score: 0.8762
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 185	score: 0.9479
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 186	score: 0.9529
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 187	score: 0.8972
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 188	score: 0.8390
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 189	score: 0.8674
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 190	score: 0.8378
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 191	score: 0.8971
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 192	score: 0.8800
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 193	score: 0.8551
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 194	score: 0.9095
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 195	score: 0.9042
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 196	score: 0.8725
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 197	score: 0.8082
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 198	score: 0.8889
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 199	score: 0.8747
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 200	score: 0.8917
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 201	score: 0.8688
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 202	score: 0.8550
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 203	score: 0.7337
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 204	score: 0.8984
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 205	score: 0.9117
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 206	score: 0.9199
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 207	score: 0.8880
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 208	score: 0.8405
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 209	score: 0.9379
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 210	score: 0.9147
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 211	score: 0.8997
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 212	score: 0.8754
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 213	score: 0.9389
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 214	score: 0.9156
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 215	score: 0.8948
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 216	score: 0.8389
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 217	score: 0.9022
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 218	score: 0.8659
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 219	score: 0.8952
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 220	score: 0.9664
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 221	score: 0.9161
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 222	score: 0.9285
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 223	score: 0.8691
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 224	score: 0.9468
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 225	score: 0.9536
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 226	score: 0.8134
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 227	score: 0.7313
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 228	score: 0.8957
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 229	score: 0.8408
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 230	score: 0.9753
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 231	score: 0.8801
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 232	score: 0.9013
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 233	score: 0.9614
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 234	score: 0.7817
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 235	score: 0.8393
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 236	score: 0.8410
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 237	score: 0.8786
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 238	score: 0.8987
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 239	score: 0.9121
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 240	score: 0.8343
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 241	score: 0.8171
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 242	score: 0.9092
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 243	score: 0.6292
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 244	score: 0.8220
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 245	score: 0.8723
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 246	score: 0.8058
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 247	score: 0.8335
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 248	score: 0.6430
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 249	score: 0.8721
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 250	score: 0.9097
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 251	score: 0.8434
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 252	score: 0.9411
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 253	score: 0.9391
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 254	score: 0.9665
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 255	score: 0.9293
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 256	score: 0.8451
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 257	score: 0.9371
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 258	score: 0.8815
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 259	score: 0.8078
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 260	score: 0.8878
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 261	score: 0.7069
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 262	score: 0.9393
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 263	score: 0.9154
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 264	score: 0.9181
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 265	score: 0.9050
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 266	score: 0.8672
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 267	score: 0.8926
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 268	score: 0.9381
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 269	score: 0.7940
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 270	score: 0.8528
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 271	score: 0.8452
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 272	score: 0.9087
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 273	score: 0.9073
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 274	score: 0.7166
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 275	score: 0.8007
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 276	score: 0.8435
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 277	score: 0.9445
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 278	score: 0.9223
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 279	score: 0.9459
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 280	score: 0.9185
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 281	score: 0.9461
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 282	score: 0.9707
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 283	score: 0.9186
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 284	score: 0.8614
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 285	score: 0.9648
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 286	score: 0.8525
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 287	score: 0.8603
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 288	score: 0.9190
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 289	score: 0.9064
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 290	score: 0.9072
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 291	score: 0.8732
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 292	score: 0.9438
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 293	score: 0.9169
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 294	score: 0.9031
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 295	score: 0.8417
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 296	score: 0.8944
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 297	score: 0.8672
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 298	score: 0.9605
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 299	score: 0.9180
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 300	score: 0.9267
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 301	score: 0.8616
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 302	score: 0.8954
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 303	score: 0.8705
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 304	score: 0.9231
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 305	score: 0.9000
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 306	score: 0.8958
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 307	score: 0.8630
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 308	score: 0.8906
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 309	score: 0.8721
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 310	score: 0.9692
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 311	score: 0.8893
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 312	score: 0.8764
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 313	score: 0.8167
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 314	score: 0.9572
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 315	score: 0.9014
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 316	score: 0.9282
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 317	score: 0.8598
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 318	score: 0.9091
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 319	score: 0.8585
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 320	score: 0.8353
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 321	score: 0.8614
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 322	score: 0.9069
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 323	score: 0.9175
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 324	score: 0.9463
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 325	score: 0.8330
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 326	score: 0.8693
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 327	score: 0.8451
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 328	score: 0.8897
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 329	score: 0.9152
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 330	score: 0.8739
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 331	score: 0.8906
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 332	score: 0.8763
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 333	score: 0.8563
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 334	score: 0.6298
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 335	score: 0.8237
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 336	score: 0.8618
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 337	score: 0.8559
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 338	score: 0.9100
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 339	score: 0.9488
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 340	score: 0.8463
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 341	score: 0.8147
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 342	score: 0.5888
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 343	score: 0.7956
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 344	score: 0.8886
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 345	score: 0.9045
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 346	score: 0.9145
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 347	score: 0.9241
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 348	score: 0.8328
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 349	score: 0.6858
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 350	score: 0.6594
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 351	score: 0.8873
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 352	score: 0.9338
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 353	score: 0.8210
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 354	score: 0.8478
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 355	score: 0.8644
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 356	score: 0.8160
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 357	score: 0.8937
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 358	score: 0.7343
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 359	score: 0.8155
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 360	score: 0.8679
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 361	score: 0.7935
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 362	score: 0.8611
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 363	score: 0.9105
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 364	score: 0.8652
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 365	score: 0.7611
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 366	score: 0.6871
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 367	score: 0.6532
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 368	score: 0.7343
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 369	score: 0.8071
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 370	score: 0.8281
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 371	score: 0.6970
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 372	score: 0.9026
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 373	score: 0.8653
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 374	score: 0.9312
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 375	score: 0.8838
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 376	score: 0.9456
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 377	score: 0.9508
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 378	score: 0.7316
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 379	score: 0.9355
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 380	score: 0.9513
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 381	score: 0.8829
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 382	score: 0.7510
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 383	score: 0.7231
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 384	score: 0.8577
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 385	score: 0.7759
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 386	score: 0.7189
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 387	score: 0.8996
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 388	score: 0.6229
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 389	score: 0.9479
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 390	score: 0.9282
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 391	score: 0.9212
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 392	score: 0.9108
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 393	score: 0.9471
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 394	score: 0.9066
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 395	score: 0.9766
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 396	score: 0.8865
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 397	score: 0.9373
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 398	score: 0.8113
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 399	score: 0.9532
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 400	score: 0.9160
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 401	score: 0.8388
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 402	score: 0.9299
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 403	score: 0.8708
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 404	score: 0.7477
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 405	score: 0.8625
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 406	score: 0.9265
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 407	score: 0.9243
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 408	score: 0.9329
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 409	score: 0.9481
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 410	score: 0.8323
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 411	score: 0.7769
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 412	score: 0.9045
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 413	score: 0.9411
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 414	score: 0.8908
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 415	score: 0.8976
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 416	score: 0.8832
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 417	score: 0.7247
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 418	score: 0.9383
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 419	score: 0.9425
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 420	score: 0.9066
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 421	score: 0.9597
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 422	score: 0.7545
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 423	score: 0.9011
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 424	score: 0.9077
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 425	score: 0.9222
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 426	score: 0.9264
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 427	score: 0.9426
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 428	score: 0.9046
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 429	score: 0.9389
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 430	score: 0.9120
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 431	score: 0.7839
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 432	score: 0.8507
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 433	score: 0.7745
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 434	score: 0.8654
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 435	score: 0.8829
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 436	score: 0.8107
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 437	score: 0.8609
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 438	score: 0.9368
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 439	score: 0.8624
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 440	score: 0.9243
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 441	score: 0.9027
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 442	score: 0.9402
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 443	score: 0.9027
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 444	score: 0.8620
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 445	score: 0.8523
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 446	score: 0.8759
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 447	score: 0.9200
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 448	score: 0.9126
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 449	score: 0.7815
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 450	score: 0.9138
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 451	score: 0.9232
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 452	score: 0.8867
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 453	score: 0.9242
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 454	score: 0.8921
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 455	score: 0.8650
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 456	score: 0.7803
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 457	score: 0.9502
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 458	score: 0.8338
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 459	score: 0.8879
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 460	score: 0.9443
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 461	score: 0.8819
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 462	score: 0.8330
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 463	score: 0.9544
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 464	score: 0.9247
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 465	score: 0.7297
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 466	score: 0.9354
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 467	score: 0.7859
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 468	score: 0.5838
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 469	score: 0.6450
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 470	score: 0.7790
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 471	score: 0.7055
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 472	score: 0.8671
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 473	score: 0.7875
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 474	score: 0.7400
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 475	score: 0.9497
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 476	score: 0.8363
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 477	score: 0.9039
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 478	score: 0.8728
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 479	score: 0.9382
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 480	score: 0.9012
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 481	score: 0.8129
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 482	score: 0.8648
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 483	score: 0.8259
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 484	score: 0.8826
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 485	score: 0.8914
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 486	score: 0.8713
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 487	score: 0.8773
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 488	score: 0.9257
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 489	score: 0.9266
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 490	score: 0.7979
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 491	score: 0.8907
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 492	score: 0.9591
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 493	score: 0.9331
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 494	score: 0.8189
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 495	score: 0.8784
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 496	score: 0.8801
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 497	score: 0.8528
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 498	score: 0.8452
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 499	score: 0.8612
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 500	score: 0.9438
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 501	score: 0.9320
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 502	score: 0.9114
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 503	score: 0.8246
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 504	score: 0.7863
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 505	score: 0.8741
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 506	score: 0.8102
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 507	score: 0.6995
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 508	score: 0.8897
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 509	score: 0.8297
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 510	score: 0.8314
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 511	score: 0.8118
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 512	score: 0.7729
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 513	score: 0.6141
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 514	score: 0.8863
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 515	score: 0.8332
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 516	score: 0.8521
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 517	score: 0.9506
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 518	score: 0.9249
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 519	score: 0.9361
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 520	score: 0.9004
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 521	score: 0.8600
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 522	score: 0.8370
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 523	score: 0.8580
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 524	score: 0.9333
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 525	score: 0.8808
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 526	score: 0.8657
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 527	score: 0.7047
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 528	score: 0.8429
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 529	score: 0.9046
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 530	score: 0.8152
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 531	score: 0.9162
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 532	score: 0.8913
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 533	score: 0.8588
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 534	score: 0.7792
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 535	score: 0.6009
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 536	score: 0.7731
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 537	score: 0.8644
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 538	score: 0.8839
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 539	score: 0.8095
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 540	score: 0.8966
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 541	score: 0.9413
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 542	score: 0.9057
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 543	score: 0.8840
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 544	score: 0.9001
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 545	score: 0.9674
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 546	score: 0.7924
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 547	score: 0.9210
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 548	score: 0.5087
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 549	score: 0.8936
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 550	score: 0.8605
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 551	score: 0.9237
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 552	score: 0.9514
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 553	score: 0.9282
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 554	score: 0.9084
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 555	score: 0.7092
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 556	score: 0.8071
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 557	score: 0.8885
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 558	score: 0.7949
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 559	score: 0.8510
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 560	score: 0.8809
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 561	score: 0.9340
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 562	score: 0.8498
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 563	score: 0.6823
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 564	score: 0.8663
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 565	score: 0.9562
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 566	score: 0.8752
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 567	score: 0.9466
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 568	score: 0.8239
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 569	score: 0.7384
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 570	score: 0.9141
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 571	score: 0.9228
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 572	score: 0.8953
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 573	score: 0.9198
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 574	score: 0.9243
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 575	score: 0.8270
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 576	score: 0.8725
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 577	score: 0.9397
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 578	score: 0.9256
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 579	score: 0.9172
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 580	score: 0.9027
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 581	score: 0.8642
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 582	score: 0.9032
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 583	score: 0.8667
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 584	score: 0.6800
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 585	score: 0.9118
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 586	score: 0.9180
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 587	score: 0.9019
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 588	score: 0.8269
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 589	score: 0.8841
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 590	score: 0.9414
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 591	score: 0.9320
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 592	score: 0.8270
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 593	score: 0.8930
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 594	score: 0.9448
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 595	score: 0.9351
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 596	score: 0.8555
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 597	score: 0.8764
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 598	score: 0.9012
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 599	score: 0.9112
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 600	score: 0.7892
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 601	score: 0.9140
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 602	score: 0.9136
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 603	score: 0.8799
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 604	score: 0.9104
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 605	score: 0.9361
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 606	score: 0.8766
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 607	score: 0.8834
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 608	score: 0.8358
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 609	score: 0.7852
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 610	score: 0.8877
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 611	score: 0.9327
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 612	score: 0.9028
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 613	score: 0.8665
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 614	score: 0.8613
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 615	score: 0.8639
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 616	score: 0.9067
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 617	score: 0.9659
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 618	score: 0.9178
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 619	score: 0.8276
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 620	score: 0.7513
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 621	score: 0.8052
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 622	score: 0.9232
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 623	score: 0.8645
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 624	score: 0.8095
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 625	score: 0.9336
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 626	score: 0.9454
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 627	score: 0.8354
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 628	score: 0.9346
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 629	score: 0.9009
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 630	score: 0.8612
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 631	score: 0.9014
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 632	score: 0.7239
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 633	score: 0.9262
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 634	score: 0.9447
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 635	score: 0.9478
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 636	score: 0.9065
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 637	score: 0.9118
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 638	score: 0.8802
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 639	score: 0.9339
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 640	score: 0.9028
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 641	score: 0.8958
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 642	score: 0.8403
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 643	score: 0.5208
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 644	score: 0.3257
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 645	score: 0.7787
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 646	score: 0.7796
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 647	score: 0.7987
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 648	score: 0.7956
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 649	score: 0.8303
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 650	score: 0.9042
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 651	score: 0.7835
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 652	score: 0.8396
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 653	score: 0.8010
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 654	score: 0.8971
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 655	score: 0.9366
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 656	score: 0.8221
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 657	score: 0.8949
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 658	score: 0.6711
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 659	score: 0.7143
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 660	score: 0.8130
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 661	score: 0.9452
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 662	score: 0.9566
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 663	score: 0.8067
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 664	score: 0.9383
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 665	score: 0.8985
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 666	score: 0.9090
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 667	score: 0.7847
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 668	score: 0.9036
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 669	score: 0.9180
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 670	score: 0.8933
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 671	score: 0.9333
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 672	score: 0.8761
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 673	score: 0.9402
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 674	score: 0.9430
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 675	score: 0.8994
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 676	score: 0.8999
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 677	score: 0.9377
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 678	score: 0.9027
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 679	score: 0.9170
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 680	score: 0.8323
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 681	score: 0.9645
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 682	score: 0.9053
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 683	score: 0.7990
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 684	score: 0.8624
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 685	score: 0.8787
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 686	score: 0.8410
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 687	score: 0.9266
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 688	score: 0.8827
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 689	score: 0.9131
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 690	score: 0.9382
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 691	score: 0.8996
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 692	score: 0.9330
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 693	score: 0.9219
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 694	score: 0.8627
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 695	score: 0.4304
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 696	score: 0.8656
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 697	score: 0.9342
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 698	score: 0.9041
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 699	score: 0.9617
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 700	score: 0.9153
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 701	score: 0.9542
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 702	score: 0.9209
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 703	score: 0.7535
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 704	score: 0.8465
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 705	score: 0.8535
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 706	score: 0.8189
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 707	score: 0.9244
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 708	score: 0.9409
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 709	score: 0.9152
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 710	score: 0.9536
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 711	score: 0.8483
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 712	score: 0.9085
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 713	score: 0.8092
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 714	score: 0.9166
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 715	score: 0.8966
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 716	score: 0.8428
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 717	score: 0.8021
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 718	score: 0.9557
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 719	score: 0.9512
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 720	score: 0.8796
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 721	score: 0.8159
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 722	score: 0.9121
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 723	score: 0.8853
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 724	score: 0.8625
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 725	score: 0.8670
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 726	score: 0.8696
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 727	score: 0.8968
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 728	score: 0.7555
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 729	score: 0.8896
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 730	score: 0.7526
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 731	score: 0.9352
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 732	score: 0.8944
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 733	score: 0.9212
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 734	score: 0.8849
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 735	score: 0.8457
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 736	score: 0.9012
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 737	score: 0.9167
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 738	score: 0.9423
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 739	score: 0.8944
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 740	score: 0.8493
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 741	score: 0.7832
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 742	score: 0.8255
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 743	score: 0.9296
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 744	score: 0.9246
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 745	score: 0.9172
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 746	score: 0.9163
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 747	score: 0.8879
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 748	score: 0.9366
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 749	score: 0.8853
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 750	score: 0.9272
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 751	score: 0.8441
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 752	score: 0.8744
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 753	score: 0.8630
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 754	score: 0.9541
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 755	score: 0.9312
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 756	score: 0.7634
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 757	score: 0.8811
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 758	score: 0.8575
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 759	score: 0.8451
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 760	score: 0.9637
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 761	score: 0.9077
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 762	score: 0.9405
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 763	score: 0.7910
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 764	score: 0.8269
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 765	score: 0.8765
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 766	score: 0.8944
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 767	score: 0.8231
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 768	score: 0.9158
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 769	score: 0.9242
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 770	score: 0.8911
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 771	score: 0.8880
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 772	score: 0.9223
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 773	score: 0.9111
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 774	score: 0.8666
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 775	score: 0.8925
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 776	score: 0.8176
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 777	score: 0.9320
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 778	score: 0.8978
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 779	score: 0.8383
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 780	score: 0.8441
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 781	score: 0.7850
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 782	score: 0.8788
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 783	score: 0.8045
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 784	score: 0.9110
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 785	score: 0.8522
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 786	score: 0.9105
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 787	score: 0.9116
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 788	score: 0.8763
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 789	score: 0.9114
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 790	score: 0.8089
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 791	score: 0.8872
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 792	score: 0.9264
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 793	score: 0.8877
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 794	score: 0.8371
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 795	score: 0.8503
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 796	score: 0.9239
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 797	score: 0.8851
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 798	score: 0.8358
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 799	score: 0.7680
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 800	score: 0.8962
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 801	score: 0.8772
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 802	score: 0.8500
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 803	score: 0.8815
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 804	score: 0.7507
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 805	score: 0.8251
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 806	score: 0.9241
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 807	score: 0.8937
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 808	score: 0.9114
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 809	score: 0.8634
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 810	score: 0.7739
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 811	score: 0.7913
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 812	score: 0.9250
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 813	score: 0.9452
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 814	score: 0.8905
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 815	score: 0.8313
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 816	score: 0.8401
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 817	score: 0.8431
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 818	score: 0.7100
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 819	score: 0.6805
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 820	score: 0.9146
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 821	score: 0.7653
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 822	score: 0.8508
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 823	score: 0.8684
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 824	score: 0.9174
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 825	score: 0.9151
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 826	score: 0.8910
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 827	score: 0.8614
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 828	score: 0.8980
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 829	score: 0.7593
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 830	score: 0.9235
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 831	score: 0.8006
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 832	score: 0.9183
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 833	score: 0.8437
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 834	score: 0.8911
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 835	score: 0.8787
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 836	score: 0.8589
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 837	score: 0.8871
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 838	score: 0.8184
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 839	score: 0.8383
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 840	score: 0.6057
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 841	score: 0.8777
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 842	score: 0.6563
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 843	score: 0.8812
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 844	score: 0.7482
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 845	score: 0.5951
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 846	score: 0.6426
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 847	score: 0.8870
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 848	score: 0.9123
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 849	score: 0.6982
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 850	score: 0.7723
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 851	score: 0.9313
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 852	score: 0.9380
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 853	score: 0.5854
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 854	score: 0.8305
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 855	score: 0.7628
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 856	score: 0.6509
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 857	score: 0.9195
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 858	score: 0.9160
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 859	score: 0.9013
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 860	score: 0.9093
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 861	score: 0.8858
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 862	score: 0.9359
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 863	score: 0.9051
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 864	score: 0.8747
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 865	score: 0.8484
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 866	score: 0.8675
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 867	score: 0.8879
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 868	score: 0.8713
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 869	score: 0.9106
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 870	score: 0.8883
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 871	score: 0.9280
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 872	score: 0.9261
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 873	score: 0.8949
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 874	score: 0.8888
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 875	score: 0.7761
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 876	score: 0.9124
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 877	score: 0.9296
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 878	score: 0.8930
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 879	score: 0.7779
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 880	score: 0.8914
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 881	score: 0.9542
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 882	score: 0.9662
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 883	score: 0.8792
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 884	score: 0.7269
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 885	score: 0.9413
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 886	score: 0.8950
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 887	score: 0.4546
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 888	score: 0.7870
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 889	score: 0.8901
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 890	score: 0.8818
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 891	score: 0.8515
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 892	score: 0.7379
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 893	score: 0.8143
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 894	score: 0.9106
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 895	score: 0.8024
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 896	score: 0.9041
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 897	score: 0.8829
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 898	score: 0.9201
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 899	score: 0.8924
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 900	score: 0.9037
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 901	score: 0.8430
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 902	score: 0.6183
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 903	score: 0.8836
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 904	score: 0.9402
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 905	score: 0.8890
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 906	score: 0.8997
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 907	score: 0.9356
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 908	score: 0.8648
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 909	score: 0.8879
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 910	score: 0.7889
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 911	score: 0.8865
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 912	score: 0.9428
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 913	score: 0.7722
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 914	score: 0.9028
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 915	score: 0.8311
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 916	score: 0.9289
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 917	score: 0.8737
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 918	score: 0.9418
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 919	score: 0.8569
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 920	score: 0.8558
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 921	score: 0.9194
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 922	score: 0.8037
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 923	score: 0.8244
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 924	score: 0.9300
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 925	score: 0.8241
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 926	score: 0.9131
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 927	score: 0.6666
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 928	score: 0.9151
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 929	score: 0.8902
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 930	score: 0.9274
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 931	score: 0.9180
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 932	score: 0.6997
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 933	score: 0.8023
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 934	score: 0.6655
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 935	score: 0.8361
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 936	score: 0.8636
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 937	score: 0.9463
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 938	score: 0.9145
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 939	score: 0.8971
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 940	score: 0.9325
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 941	score: 0.9569
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 942	score: 0.9495
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 943	score: 0.8613
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 944	score: 0.8785
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 945	score: 0.8192
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 946	score: 0.8735
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 947	score: 0.8737
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 948	score: 0.7793
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 949	score: 0.8978
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 950	score: 0.8460
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 951	score: 0.8278
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 952	score: 0.7921
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 953	score: 0.7064
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 954	score: 0.6535
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 955	score: 0.9022
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 956	score: 0.9094
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 957	score: 0.9661
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 958	score: 0.8787
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 959	score: 0.9248
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 960	score: 0.7775
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 961	score: 0.8956
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 962	score: 0.9158
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 963	score: 0.8996
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 964	score: 0.8882
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 965	score: 0.8975
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 966	score: 0.8604
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 967	score: 0.6629
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 968	score: 0.7983
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 969	score: 0.8671
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 970	score: 0.8356
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 971	score: 0.8637
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 972	score: 0.9044
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 973	score: 0.8386
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 974	score: 0.7575
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 975	score: 0.9329
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 976	score: 0.8578
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 977	score: 0.8611
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 978	score: 0.8942
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 979	score: 0.8861
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 980	score: 0.8255
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 981	score: 0.8627
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 982	score: 0.9354
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 983	score: 0.8424
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 984	score: 0.8477
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 985	score: 0.8936
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 986	score: 0.9172
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 987	score: 0.8744
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 988	score: 0.7340
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 989	score: 0.7138
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 990	score: 0.9373
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 991	score: 0.7902
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 992	score: 0.9488
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 993	score: 0.8645
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 994	score: 0.8453
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 995	score: 0.8761
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 996	score: 0.9511
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 997	score: 0.9679
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 998	score: 0.8673
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 999	score: 0.8682
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 1000	score: 0.9243
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 1001	score: 0.8694
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 1002	score: 0.8579
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 1003	score: 0.8774
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 1004	score: 0.8768
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 1005	score: 0.9187
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 1006	score: 0.9208
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 1007	score: 0.8884
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 1008	score: 0.9570
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 1009	score: 0.8973
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 1010	score: 0.8594
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	Segment 1011	score: 0.8789
+/beacon-scratch/tongzh24/ALMA-checkpoint/exp_50_languages/alma-13b-sft-group-5-max-tokens-512//test-en-hu	score: 0.8669